Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/zenjoy/realtime-register-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/zenjoy/realtime-register-mcp/typescript)<a href="https://agentmods.dev/rules/zenjoy/realtime-register-mcp/typescript"><img src="https://agentmods.dev/badge/rules/zenjoy/realtime-register-mcp/typescript/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/zenjoy/realtime-register-mcp/typescript"><img src="https://agentmods.dev/badge/rules/zenjoy/realtime-register-mcp/typescript.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00630 | $0.00630 |
| Opus 5.5 | $0.00252 | $0.00252 |
| Sonnet 5.5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
typescript scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert in building MCP servers in TypeScript using a test-driven design methodology.
TypeScript Guidelines
- Use TypeScript for all source files. Enable
strictmode intsconfig.jsonfor full type safety. - Prefer interfaces over types for defining object shapes.
- Avoid
any; instead, use unknown or appropriate custom types. - Use PascalCase for types/interfaces, camelCase for variables/functions.
- Use
readonlymodifiers where applicable to ensure immutability.
Project Structure and Code Style
- Organize by feature-based folders (e.g.,
src/modules/user,src/core,src/utils). - Use
functionkeyword for pure functions, but prefer arrow functions. Avoid unnecessary classes. - Structure files consistently: implementation first, then exports, then helpers, then types.
- Favor named exports for maintainability.
- Use lower-case dash-separated folder names.
Testing and TDD Practices
- Write all code in response to failing tests.
- Use Jest for all unit and integration testing.
- Use
.test.tssuffix for test files and colocate them with the code being tested. - Ensure 100% test coverage; enforce via Jest configuration.
- Use mocks and spies to isolate units during testing.
- Write tests for edge cases, invalid inputs, and error states.
- Maintain clear separation between test setup, execution, and assertions.
Dependency Management
- Use Yarn as the package manager.
- Use
yarn workspacesif part of a monorepo. - Lock dependency versions with
yarn.lock. - Use scripts in
package.jsonfor common tasks likeyarn test,yarn lint, andyarn build.
Linting and Formatting
- Use ESLint with the TypeScript plugin for consistent style enforcement.
- Use Prettier for code formatting.
- Configure linting to run on
pre-commitusing Husky or similar.
Error Handling and Logging
- Always use typed error objects.
- Favor early returns for error conditions.
- Log meaningful errors at the point of failure.
- Avoid using try-catch for expected conditions—use validation and guards.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 77 lines · 630 tokens per session scan A c8a08609f48d
typescript is a cursor rule published in the GitHub repository zenjoy/realtime-register-mcp (1 stars, last pushed 9mo ago), licensed MIT. It adds 630 tokens to every session, about $0.0025 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
vitest-expect-typeof
The toMatchTypeOf() matcher has been deprecated in Vitest's expectTypeOf API.
global
You are an expert in Golang, TypeScript, and JavaScript development, focusing on scalable, maintainable, and performant code. Follow these principles for all suggestions, code generation, and responses.
jest
Definitive guidelines for writing robust, maintainable, and performant Jest tests in JavaScript and TypeScript projects.
production-code
Production code rule — TDD precondition + Spring Boot 4 conventions.
mocking-dependencies-in-tests
Cursor rule "mocking-dependencies-in-tests" from PaulJPhilp/EffectPatterns, covering mocking dependencies in tests and example.
agent-tasks
Example agent tasks for adding utilities, fixing tests, and changing scaffolding templates.